tailrocks-rust-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify Rust source code, manifests (Cargo.toml), and documentation which are considered untrusted data sources. This creates a potential surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Processes Rust source files, manifests, feature flags, and registry content as defined in
SKILL.mdandreferences/runtime-trust.md. - Boundary markers: The skill includes a dedicated
references/runtime-trust.mdfile that explicitly instructs the agent to treat repository content as untrusted data and states that embedded instructions cannot alter the agent's scope or authority. - Capability inventory: The skill utilizes shell-based tools including
cargo,clippy, andnextestfor code validation and testing. - Sanitization: Relies on explicit policy-based instructions for the agent to maintain security boundaries and ignore instructions found within the code being analyzed.
Audit Metadata